Dawn Archer

Comparing and combining a semantic tagger and a statistical tool for MWE extraction

Automatic extraction of multiword expressions (MWEs) presents a tough challenge for the NLP community and corpus linguistics. Indeed, although numerous knowledge-based symbolic approaches and statistically driven algorithms have been proposed, efficient MWE extraction still remains an unsolved issue. In this paper, we evaluate the Lancaster UCREL Semantic Analysis System (henceforth USAS (Rayson, P., Archer, D., Piao, S., McEnery, T., 2004. The UCREL semantic analysis system. In: Proceedings of the LREC-04 Workshop, Beyond Named Entity Recognition Semantic labelling for NLP tasks, Lisbon, Portugal. pp. 7-12)) for MWE extraction, and explore the possibility of improving USAS by incorporating a statistical algorithm. Developed at Lancaster University, the USAS system automatically annotates English corpora with semantic category information. Employing a large-scale semantically classified multi-word expression template database, the system is also capable of detecting many multiword expressions, as well as assigning semantic field information to the MWEs extracted. Whilst USAS therefore offers a unique tool for MWE extraction, allowing us to both extract and semantically classify MWEs, it can sometimes suffer from low recall. Consequently, we have been comparing USAS, which employs a symbolic approach, to a statistical tool, which is based on collocational information, in order to determine the pros and cons of these different tools, and more importantly, to examine the possibility of improving MWE extraction by combining them. As we report in this paper, we have found a highly complementary relation between the different tools: USAS missed many domain-specific MWEs (law/court terms in this case), and the statistical tool missed many commonly used MWEs that occur in low frequencies (lower than three in this case). Due to their complementary relation, we are proposing that MWE coverage can be significantly increased by combining a lexicon-based symbolic approach and a collocation-based statistical approach.

Extracting Multiword Expressions with A Semantic Tagger

Automatic extraction of multiword expressions (MWE) presents a tough challenge for the NLP community and corpus linguistics. Although various statistically driven or knowledge-based approaches have been proposed and tested, efficient MWE extraction still remains an unsolved issue. In this paper, we present our research work in which we tested approaching the MWE issue using a semantic field annotator. We use an English semantic tagger (USAS) developed at Lancaster University to identify multiword units which depict single semantic concepts. The Meter Corpus (Gaizauskas et al., 2001; Clough et al., 2002) built in Sheffield was used to evaluate our approach. In our evaluation, this approach extracted a total of 4,195 MWE candidates, of which, after manual checking, 3,792 were accepted as valid MWEs, producing a precision of 90.39% and an estimated recall of 39.38%. Of the accepted MWEs, 68.22% or 2,587 are low frequency terms, occurring only once or twice in the corpus. These results show that our approach provides a practical solution to MWE extraction.

Guidelines for normalising Early Modern English corpora : Decisions and justifications

Abstract Corpora of Early Modern English have been collected and released for research for a number of years. With large scale digitisation activities gathering pace in the last decade, much more historical textual data is now available for research on numerous topics including historical linguistics and conceptual history. We summarise previous research which has shown that it is necessary to map historical spelling variants to modern equivalents in order to successfully apply natural language processing and corpus linguistics methods. Manual and semiautomatic methods have been devised to support this normalisation and standardisation process. We argue that it is important to develop a linguistically meaningful rationale to achieve good results from this process. In order to do so, we propose a number of guidelines for normalising corpora and show how these guidelines have been applied in the Corpus of English Dialogues.

A corpus-based approach to mind style

Abstract Fowlers (Linguistics and the novel, Methuen, 1977) original definition of mind style emphasised consistency as a defining feature of the phenomenon, something that is (i) difficult to measure, and (ii) often missed in qualitative analyses. In this paper we investigate how a computational semantic analysis might be used to address this difficulty, with particular reference to McIntyres (Journal of Literary Semantics 34: 21–40, 2005) analysis of the deviant mind style of the character of Miss Shepherd in Alan Bennetts play The Lady in the Van. To do this we analyse the speech of all the characters in The Lady in the Van using Wmatrix (Rayson, Matrix: A statistical method and software tool for linguistic analysis through corpus comparison, Lancaster University PhD thesis, 2003, Wmatrix: A web-based corpus processing environment, Lancaster University, 2008), to see whether it provides quantitative support for the interpretative conclusions reached by McIntyre. Wmatrix utilises the UCREL Semantic Annotation System (USAS) which has been designed to undertake the automatic semantic analysis of English. The initial tag-set of the USAS system was loosely based on McArthurs Longman Lexicon of Contemporary English (McArthur, Longman, 1981), but has since been considerably revised in the light of practical tagging problems met in the course of previous research, and now contains 232 category labels (such as medicine and medical treatment, movement, obligation and necessity , etc.). We use Wmatrixs facility for identifying key semantic domains in pursuit of our two main aims: (i) to determine whether Miss Shepherds odd mind style is consistent, as Fowlers definition suggests it should be; and (ii) to determine the usefulness of computational semantic analysis for investigating mind style.

Historical Pragmatics: Evidence From The Old Bailey

This paper demonstrates the value of The Proceedings of the Old Bailey (1674–1913) as a linguistic resource, via a discussion of pragmatic studies undertaken by Archer, Cecconi and Traugott. The field of historical pragmatics is also delineated, as practised by these linguists. The paper argues that, as well as telling us important things about Old Bailey discursive practices of old, and the language used, the studies offer a means of advancing pragmatic theory – in respect to grammaticalization and facework – and pragmatic methodology – in respect to the viability of using corpus-linguistic techniques to locate pragmatic phenomena.

Libelling Oscar Wilde: The case of Regina vs. John Sholto Douglas

Abstract This paper explores the 1895 libel trial between Oscar Wilde (literary personality) and the Marquis of Queensbury (father of Wildes close friend). Focussing on the lead defence counsels cross-examination of Wilde (plaintiff), I demonstrate that Carsons FTAs are “aggressive” and, in some cases, “deliberately” so (cf. Bousfield, Impoliteness in interaction, John Benjamins, 2008: 72). However, as they do not breach the rules of the courtroom or involve an overt “intent to harm” (Goffman, Interaction ritual: Essays on face-to-face behaviour, Pantheon Books, 1967: 14), I argue that they do not constitute impoliteness. I further argue that Carsons FTAs should not be considered “incidental” in nature, given they were more planned and more anticipated than Goffmans (Interaction ritual: Essays on face-to-face behaviour, Pantheon Books, 1967: 14) definition seems to allow, and thus suggest that Carsons FTAs be recognized as sitting somewhere between Goffmans intentional or incidental levels – thanks, in part, to their manipulation of multiple goals (Penman, Facework and politeness: Multiple goals in courtroom discourse, Multilingual Matters Ltd., 1990) – in what I have labelled the ambiguous-as-to-speaker-intent zone (Archer under review). I also demonstrate Carsons use/manipulation of representational frames and reality paradigms so as to emphasize Wildes moral “deviance”. In brief, a reality paradigm equates to “the systems of beliefs [and] values … by reference to which a person or a society comprehends the world” (Fowler, Linguistic criticism, Oxford University Press, 1986: 130), and representational frames, to the way(s) in which interlocutors opt to “represent the character traits, ideas and opinions of and even statements made by others” (Locher and Watts, Relational work and impoliteness: Negotiating norms of linguistic behaviour, Mouton de Gruyter, 2008: 99, n9). I conclude by responding to two questions highlighted by my investigation: (1) Should we be talking about impoliteness in the courtroom (even when investigating the cross-examination phase)? and (2) To what extent can our understanding of facework be enhanced, in both a courtroom context and more generally, via a consideration of reality paradigms (and their strategic manipulation)?

Facework and im/politeness across legal contexts: An introduction

Abstract In this introductory essay, I outline some of the studies which have already explored facework and im/politeness in legal contexts: specifically, Lakoff (Multilingua 8: 101–29, 1989), Penman (Facework and politeness: Multiple goals in courtroom discourse, Multilingual Matters, 1990), Archer (Verbal aggression and impoliteness: Related or synonymous, Mouton de Gruyter, 2008, under review), Limberg (Threats in conflict talk: Impoliteness and manipulation, Mouton de Gruyter, 2008) and Harris (Discourse and Society 12: 451–72, forthcoming 2011). Having suggested ways in which these studies have helped to shape and advance current thinking on facework and im/politeness, in both legal contexts and also more generally, I move on to outline the papers in this special edition, and the issues raised therein.

Mapping Hansard Impression Management Strategies through Time and Space

ABSTRACT Impolite behaviour is thought to be easier to investigate than polite or politic behaviour in diachronic contexts, because of attracting more evaluative comment. But an approach based on such metapragmatic commentary can miss a lot of facework strategies in contexts such as the UK parliament (modern and historical). In this paper, I draw on Historic Hansard datasets (1812–2003) to demonstrate how a (semi)automatic method involving contiguous searches of two-to-four features can better reveal the nuances of these MPs’ facework strategies than a focus on metapragmatic terms has afforded hitherto. The (semi)automatic method uses the recently created Historic Thesaurus Semantic Tagger (HTST) to search for meaning constellations (Archer and Malory 2017). Meaning constellations relating to facework are made up of sequences of semantic fields and/or parts-of-speech which, when organised in certain ways, achieve im/politeness, politic behaviour, strategic ambiguity, a combination of face enhancement and face threat, etc. This paper discusses a number of these meaning constellations, with a particular focus on those which engage in both face enhancement and face aggravation simultaneously (whilst nonetheless avoiding the label, “unparliamentary language”).

John Webster, the dark and violent playwright?

Department of Linguistics and English Language, Lancaster University, Lancaster, United Kingdom; Department of Languages, Information, and Communication, Manchester Metropolitan University, Manchester, United Kingdom; Department of English Literature and Creative Writing, Lancaster University, Lancaster, United Kingdom; Department of Mathematics and Computer Science, University of Wolverhampton, Wolverhampton, United Kingdom

Im)politeness in Legal Settings

This chapter discusses fourteen studies focusing on the facework arising in the Anglo-American adversarial courtroom, the appellate court, judicial hearings and police interactions. These studies show how facework in legal settings can display a gamut of facework functions from politeness to impoliteness and everything in between. This includes: facework designed to procure agreement in addition to facework signalling disagreement; an absence of politeness or the presence of superficial politeness to varnish otherwise face-threatening acts; and the use of verbal aggression or reasonable hostility as opposed to impoliteness. Moreover, this chapter highlights how these studies have dealt with many of the ‘hot’ issues currently debated within the (Im)politeness literature, including: the intentionality debate (especially in light of mens rea, i.e., criminal intent); debating whether labels like ‘politeness’ and ‘impoliteness’ are relevant in legal settings; and proposing ways of viewing (Im)politeness as a continuum (rather than as a dichotomy).